Cover Image

When Agents Persuade: Rhetoric Generation and Mitigation in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jose, Julia, Roongta, Ritik, Greenstadt, Rachel
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Blocking to Breaking: Evaluating the Impact of Adblockers on Web Usability
by: Roongta, Ritik, et al.
Published: (2024)

Are Large Language Models Good at Detecting Propaganda?
by: Jose, Julia, et al.
Published: (2025)

Large-Scale Analysis of Persuasive Content on Moltbook
by: Jose, Julia, et al.
Published: (2026)

Persuadability and LLMs as Legal Decision Tools
by: Suttle, Oisin, et al.
Published: (2026)

Emergent Persuasion: Will LLMs Persuade Without Being Prompted?
by: Chang, Vincent, et al.
Published: (2025)

It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics
by: Kowal, Matthew, et al.
Published: (2025)

When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making
by: Fan, Shutong, et al.
Published: (2026)

How LLMs Are Persuaded: A Few Attention Heads, Rerouted
by: Sun, Xiangkun, et al.
Published: (2026)

How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
by: Zeng, Yi, et al.
Published: (2024)

When AI Gets Persuaded, Humans Follow: Inducing the Conformity Effect in Persuasive Dialogue
by: Sasaki, Rikuo, et al.
Published: (2025)

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
by: Sun, Zhongxiang, et al.
Published: (2026)

SelectLLM: Can LLMs Select Important Instructions to Annotate?
by: Parkar, Ritik Sachin, et al.
Published: (2024)

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
by: Jaipersaud, Brandon, et al.
Published: (2025)

When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs
by: Yu, Fangyi
Published: (2025)

Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Reliance in Conversational AI
by: Yazan, Mert, et al.
Published: (2026)

Anchor: Mitigating Artifact Drift in Agent Benchmark Generation
by: Ivanov, Maksim, et al.
Published: (2026)

Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs
by: Unlu, Eren
Published: (2026)

When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs
by: Yamin, Khurram, et al.
Published: (2026)

Generative Adversarial Reviews: When LLMs Become the Critic
by: Bougie, Nicolas, et al.
Published: (2024)

Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs
by: Cullen, Carissa, et al.
Published: (2026)

Driver Assistant: Persuading Drivers to Adjust Secondary Tasks Using Large Language Models
by: Xiang, Wei, et al.
Published: (2025)

Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges
by: Lee, Yunseo, et al.
Published: (2025)

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent
by: Wu, Xinyi, et al.
Published: (2026)

GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding
by: Wang, Rongzheng, et al.
Published: (2025)

Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
by: Lin, Chenchen, et al.
Published: (2026)

Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs
by: Zou, Chelsea, et al.
Published: (2025)

When Agents Evolve, Institutions Follow
by: Fei, Chao, et al.
Published: (2026)

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning
by: Chen, Liuji, et al.
Published: (2026)

PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines
by: Tapwal, Riya, et al.
Published: (2026)

Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning
by: Zhu, Ting, et al.
Published: (2024)

When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
by: Li, Xiaoxiao
Published: (2026)

Multi-Agent LLMs for Generating Research Limitations
by: Azher, Ibrahim Al, et al.
Published: (2025)

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs
by: Khairi, Ammar, et al.
Published: (2025)

From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?
by: Xu, Binyan, et al.
Published: (2026)

Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles
by: Zeng, Yongchao, et al.
Published: (2025)

Useful Memories Become Faulty When Continuously Updated by LLMs
by: Zhang, Dylan, et al.
Published: (2026)

Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs
by: Dubey, Shivam
Published: (2025)

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
by: Liu, Minqian, et al.
Published: (2025)

When Agents Disagree With Themselves: Measuring Behavioral Consistency in LLM-Based Agents
by: Mehta, Aman
Published: (2026)

Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
by: Kasat, Aryan, et al.
Published: (2026)